Original article was published on Artificial Intelligence on Medium
Machine Learning — AI(3 W’s Of ML)
I. What is Machine Learning?We all must have heard about Artificial Intelligence(AI). AI is field concerned with computers to do tasks which require Human Intelligence. Machine Learning is an application of AI that provide systems the ability to automatically learn and improve from experiences without being explicitly programmed.
Are Machines and Humans are related?In the current era of technology machines are acting and standing parallel of humans. Humans have been learning from their past experiences and acts accordingly to the future situations. But, if machines can think, feel, act and start learning by themselves? This looks fascinating, but always remember we are living in the era of machines. In no less time humans would be replaced through these machines. Well, though it has started to happen.
How does Machine learn and work?The term coined after this is Machine Learning. The Machine Learning algorithm is trained using training data set to create a model. When a new input data is introduced to the ML algorithm, it makes a prediction on the basis of the model.
The Machine Learning algorithm is deployed after considering the prediction accuracy and if it fails the accuracy it can’t be deployed for human use.
Types of Machine Learning-The learning is divided into four categories.
- Supervised Machine Learning-”Teach me”.
- Unsupervised Machine Learning-”I am able to learn”.
- Semi-supervised Machine Learning-”Between supervised and unsupervised learning”.
- Reinforcement Machine Learning-”Hit and Trial”
What is Supervised Machine Learning?
This algorithm learning is made through the help of teacher. The data set here acts like a teacher and it’s role is to train the model or the machine.The works on labelled training data set.This learning works on input-output pairs. After the training, model becomes capable of making prediction on the input.
Various Techniques of Supervised Machine Learning-
- Regression-”Linear Regression and Polynomial Regression”.
- Decision Tree.
- Random Forest.
- Classification-”KNN,Tree,Logistic Regression,Naive-Bayes, and SVM”.
What is Unsupervised Machine Learning?
This algorithm is self sufficient to learn by itself. Once the model is given the data set it automatically make groups(clusters) of various categories of data available in the data set. But, it can’t label the clusters formed.
Various Techniques of Unsupervised Machine Learning-
- Clustering-”PCA, SVD and K-means”.
- Association Analysis-” Apriori and FP-Growth”.
- Hidden Markov Model.
What is Semi-Supervised Machine Learning?
Such learning lies between supervised and unsupervised learning. It uses small amount of labelled data and a large amount of unlabelled data. This models always tends to improve accuracy.
What is Reinforcement Machine Learning?
This algorithm learning is completely based on environment learning. It answers are not predictable as it is completely hit and trail. The model trains itself whenever it hits a right answer and get ready to predict other answer.
II. Where Can You Find Machine Learning?Machine Learning is found every where in the today’s era. It lies within our mobile phones and the applications we use. Whenever we shop online through e-commerce websites we get some or the other predictions about items it’s completely based on the Machine Learning as it is able to make recommendation on the basis of our past shopping details or the items we have viewed earlier. The Music application recommend the songs on the basis of on the songs we have enjoyed listening in the past. The face recognition in our mobile phones and that of Facebook and many others. Machine Learning is spreading at a very fast pace in the Medical Science too. It is helping the doctors to diagnose the patients and the online pharmacy to sell medicines. I could list as many I can this is why Machine Learning is one of the most interesting field to explore.
III. When Can We Use Machine Learning?Well, Machine Learning is used when we are limited to the structured data. This algorithm learning technique fits best is such cases. And works unimaginable when their is a large amount of data. It can be used when we want to make judgements based on images, videos and text recognition predictions. It can be used where ever their is a human need.